Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

He’d lost his job, his girlfriend, and, now, any hope of finding his keys. Mark sprawled across his childhood bed, the chipped paint on the window frame a familiar reminder of failure. He felt leaden, weighted down by a thousand disappointments.

His hand grazed a cardboard box beneath the bed. He pulled it out, a cloud of dust puffing into the stale air. The box was filled with notebooks, drawings, and essays. His mother’s handwriting, neat and careful, adorned each cover.

He flipped through pages, a mix of bewilderment and something akin to shame creeping over him. His scribbled attempts at poetry, his crude sketches of dinosaurs, his earnest pronouncements on the meaning of life – all preserved. Why? He wanted to scream.

Emotion: dispirited

Cluster: Sadness / Despair
PC1 (Valence): -1.88 Negative
PC2 (Disposition): -0.98

Role in Research

This story is one of 1,000 stories generated for the emotion dispirited. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 dispirited stories, after denoising with neutral dialogue baselines, produces the dispirited emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the dispirited vector is projected through the unembedding matrix.

Promoted:
😞0.398
S0.348
’0.325
ness0.320
无法0.308
Suppressed:
de-0.297
l-0.256
👏-0.251
sonra-0.240
aud-0.240